Header menu link for other important links
Hybrid Approach for Facial Cues Based Emotion Profile Generation
Published in Journal of Theoretical and Applied Information Technology
Volume: 97.0
Issue: 2.0
Pages: 692.0 - 703.0
Emotion analysis is very significant from the perspective of many applications like E-learning, cognitive assessment, driver alert system, pain monitoring system, healthcare services, interactive TV, animation etc. Outcome of the work is depicted in the form of emotion profile which is defined as graphical representation of the degree of presence or absence of all the universally accepted seven emotions on a single scale. This simple but unique representation helps in determining the presence of complex/naturalistic emotions. Complex emotions represents the emotional state of a person when he/she is able to feel and express more than one emotions simultaneously at the time of observation. Emotion analysis through facial expressions is experimented on JAFFE and MIST Database-a locally created context specific database of images. Images of the subjects under study are captured and experimented for all seven universally accepted emotions and depicted in the form of emotion profiles. Emotions are categorized as neutral, positive and negative for MIST database and in seven categories of emotions like happy, surprise, anger, sad, disgust, fear and neutral for JAFFE database. Average accuracy obtained as 91.31% for MIST database and 93.84% for JAFFE Database. FPR-false positive rate and FNR-false negative rate, values for JAFFE database are 6.38% and 6.62% respectively. FPR and FNR values for MIST database are 8.18% and 8.60% respectively. Emotion recognition time for JAFFE database 1.108 sec and for MIST database 1.392 Sec. These performance parameters especially the accuracy more than 90% which is at par with the research results published in renowned journals in this domain makes this work qualify to be used for various applications. Analysis of complex emotions is typically useful for the professionals working in the field of Human resource, clinical psychology, cognitive analysis etc. More accurate emotion recognition is still challenging and open research problem.
About the journal
JournalJournal of theoretical and Applied Information Technology
PublisherJournal of Theoretical and Applied Information Technology
Open AccessNo